Estimating the optimal mix design of silica fume concrete using biogeography-based programming

Abstract

The use of silica fume in concrete mixtures has been dramatically increased in concrete industry, especially for achieving high strength concrete. An accurate model of estimating the compressive strength and optimal mix design of silica fume concrete can save in time and cost. In this study, the biogeography-based programming (BBP) was used as a symbolic regression method to predict the compressive strength of silica fume concrete, while the constrained biogeography-based optimization (CBBO) was used to estimate its optimal mix design. For this purpose, a comprehensive database was gathered from various published documents. From the collected data, about 75% of all data was employed to train the model, while the rest was used to verify the developed model. The amounts of cement, water, silica fume, coarse aggregate, fine aggregate, superplasticizer, as well as the maximum size of aggregate and concrete age were selected as the effective input variables of the model. The compressive strength of silica fume concrete was considered as the only output variable. The results show that the BBP model can be successfully used for the prediction of the compressive strength of silica fume concrete with acceptable accuracy. In addition, a graphical user interface was designed which allows the users to estimate the optimal mix design of silica fume concrete.